Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Mobile edge computing system task scheduling method based on migration and reinforcement learning

A technology of reinforcement learning and edge computing, applied in neural learning methods, computing, program control design, etc.

Active Publication Date: 2020-10-30
NORTHWESTERN POLYTECHNICAL UNIV +1
View PDF5 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, resource allocation on mobile edge computing has become a new challenge

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Mobile edge computing system task scheduling method based on migration and reinforcement learning
  • Mobile edge computing system task scheduling method based on migration and reinforcement learning
  • Mobile edge computing system task scheduling method based on migration and reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] Attached as follows figure 1 , to further describe the application scheme:

[0063] Aiming at the task scheduling problem of edge computing servers, the present invention proposes a task scheduling method for mobile edge computing systems based on migration and reinforcement learning, which includes the following steps:

[0064] Step 1, establish a multi-agent simulation training environment, construct the reward function r of the environment, which is negatively correlated with the total consumption: r=K·e -C , where K is an adjustable coefficient, which constrains the value range of the reward function between (0, K), and C is calculated according to the integrated delay and energy consumption:

[0065] C=∑ m E. n～π(m) (c m,n )+∑ n∈N′ l n (1)

[0066] Where π(m) is the deployment strategy of the mth server, N′ is the set of users who have not obtained the server, l n is the consumption performed locally by the user. c m,n =λ 1 T m.n +λ 2 E. m,n ,T m.n ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Aiming at the task scheduling problem of an edge computing server, the invention provides a mobile edge computing system task scheduling method based on migration and reinforcement learning. The method comprises the following steps: constructing an Actor-Critic network for each server to train a scheduling strategy of the server, wherein the Actor network determines the action according to the state of the Actor network, and the Critic network evaluates the quality of the action according to the actions and the states of all the servers. And all the servers share one Critic network. When a plurality of edge server scheduling strategies are trained by using multi-agent reinforcement learning, a strategy network with the same structure is constructed for the scheduling strategy of each server. These policy networks not only have the same network layer, but also have the same number of nodes in each layer. The strategies are trained by using a centralized training decentralized executionmechanism, so that the problem of dimensionality disasters caused by too many servers is avoided.

Description

technical field [0001] The invention is used to realize task allocation and scheduling of mobile edge computing, belongs to the field of machine learning and edge computing, and specifically relates to a task scheduling method of a mobile edge computing system based on migration and reinforcement learning. Background technique [0002] Mobile devices, mainly smartphones and tablets, have become a necessity. With the continuous upgrading of mobile devices and the continuous maturity of 5G and AI technologies, people have higher and higher requirements for mobile devices, and there are more and more calls for using mobile devices for online games, image processing and virtual reality applications. Due to the limitation of the size of the mobile device itself, it is difficult to rely on an independent processor to achieve complex calculations, not to mention calculation-intensive and resource-intensive calculations. In order to address this problem, researchers proposed mobile...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F9/48G06F9/50G06N3/04G06N3/08
CPCG06F9/4843G06F9/5061G06N3/08G06N3/045
Inventor 冷立雄马占国宫业国
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com